Skip to content

[llm] fix lora #9659

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wawltor merged 1 commit into from
Dec 19, 2024
Merged

[llm] fix lora #9659

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion paddlenlp/peft/lora/lora_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,7 @@ def __init__(self, model, lora_config: LoRAConfig) -> None:
self.is_pipelinemodel = True
self.model._single_to_pp_mapping = None
if (self.lora_config.tensor_parallel_degree > 1 or self.is_pipelinemodel) and (
self.lora_config.lora_use_mixer or self.use_mora
self.lora_config.lora_use_mixer or self.lora_config.use_mora
):
raise NotImplementedError("lora_use_mixer or mora is not supported in tensor parallel mode.")
if self.lora_config.tensor_parallel_degree != self.model.config.tensor_parallel_degree:
Expand Down